# Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion

arXiv: https://arxiv.org/abs/2005.09756 · HTML: https://mlsanity.com/paper/2005.09756/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2020.

## Built on by (most cited first, 6 of 6)

- [Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator](https://mlsanity.com/paper/2205.09058/) (2022)
- [Language model fusion for streaming end to end speech recognition](https://mlsanity.com/paper/2104.04487/) (2021)
- [Integrating Lattice-Free MMI into End-to-End Speech Recognition](https://mlsanity.com/paper/2203.15614/) (2022)
- [Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture](https://mlsanity.com/paper/2203.15833/) (2022)
- [Memory Augmented Lookup Dictionary based Language Modeling for Automatic Speech Recognition](https://mlsanity.com/paper/2301.00066/) (2022)
- [Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition](https://mlsanity.com/paper/2411.17537/) (2024)

## Abstract (arXiv)

Proper nouns present a challenge for end-to-end (E2E) automatic speech recognition (ASR) systems in that a particular name may appear only rarely during training, and may have a pronunciation similar to that of a more common word. Unlike conventional ASR models, E2E systems lack an explicit pronounciation model that can be specifically trained with proper noun pronounciations and a language model that can be trained on a large text-only corpus. Past work has addressed this issue by incorporating additional training data or additional models. In this paper, we instead build on recent advances in minimum word error rate (MWER) training to develop two new loss criteria that specifically emphasize proper noun recognition. Unlike past work on this problem, this method requires no new data during training or external models during inference. We see improvements ranging from 2% to 7% relative on several relevant benchmarks.